Page 1
Page 2
The business scene continues to change
dramatically. To keep pace and to maintain
competitive positioning, mission critical
computing systems have also been changing.
Flexibility gained by the use of distributed
processing, and cost constraints on business,
have seen a growing movement from hostcentric computing to client server. Now there
is network computing using commodity
products via the Internet/Intranet.
Under these conditions, it is essential that
the new commodity networked systems
should not only have high enough
performance to process any increases in data
load, but also the highest levels of RAS
(Reliability, Availability, Serviceability) and a
standard architecture that delivers solutions
compatible to your business. Fujitsu's
promise is to deliver such support to your
business with its new industry standard UNIX
server series
-
GP7000F. GP7000F uses the
new high- performance processor, the
SPARC64 GP, the international standard
Solaris operating system, and delivers
excellent levels of RAS.
The GP7000F
UNIX servers
Page 3
GP7000F provides scalability through three distinct models and clustering:
Model 200 is scalable to two processors, Model 400 to four processors,
and Model 600 to eight processors.
Model 200/200R
High-performance entry-level server for workgroups
Each entry-level model supports up to two SPARC64 GP processors. But,
despite being an entry-level model, it also supports multi-processor clusters
to provide you with even greater performance and advanced levels of RAS.
High-performance processor SPARC64 GP (225/250/300MHz) 1 or 2
International standard "Solaris" operating system
Fujitsu RAS (Reliability, Availability, Serviceability) including System Monitoring
Module
Model 600/600R
Mission Critical server with high RAS
and performance
This high-performance server supports up to eight SPARC64 GP
processors. Its built-in RAS strategy supports mission critical operation.
Up to eight high-performance SPARC64 GP processors per cabinet
International standard "Solaris" operating system
High expandability (Max. memory: 16GB, Max. disk capacity: 70TB)
Scalable in clusters up to 128 processors
Fujitsu RAS (Reliability, Availability, Serviceability) including System Monitoring
Module
-
A New Generation of Standard
Model 400A/400R
Highly expandable mid-range client/server
application server
This mid-range server supports up to four SPARC64 GP processors,
and with 12 PCI slots provides plenty of expansion capability.
Up to four SPARC64 GP high-performance processors (250/300MHz)
International standard "Solaris" operating system
High growth capability (Max. memory: 8GB, Max. disk capacity: 60TB)
Fujitsu RAS (Reliability, Availability, Serviceability) with hot-swap/ redundant
components (Disk/PSU/FAN) including a System Monitoring Module
Page 4
GP7000F model 200R
GP7000F model 400R
"Solaris" - a global standard operating system
64-bit operating environment
Standards
The GP7000F operating system "Solaris7" offers a
powerful 64-bit computing environment. Solaris7's 64-bit
addressing supports very large memory and file systems
(1TB). It also provides superior performance on heavily
loaded systems such as data warehousing. Solaris7
provides binary compatibility with current 32-bit Solaris
applications. As a result, your software investments are
protected
-
and so is your future.
Year 2000 Compliance: follows X/Open® guidelines
Interface Standards: X/Open UNIX 98
Graphics Standards: X11, PostScriptTM, Display PostScriptTM,
OpenGL
Desktop Standards: CDE (Common Desktop Environment), Motif
Object Standards: Java IDL
Connectivity Standards: ONCTM, ONC+TM, NFS, WebNFSTM,
and optional NetWare IPX/SPX, SNA, SMB, AppleTalk, DECnet,
and others
Internet Standards: HTTP, FTP, Telnet, DNS, NTP, IMAP4,
DHCP, SNMP, SMTP
LDAPv3IETF RFCs 1323, 1510, 1652, 1869, 1870, 1891-1894,
1985, 1996, 2018, 2136, 2045, 2078
Network
Solaris offers an excellent base for network computing,
including "ONC+" that integrates network protocols
between different machines and dispersed services. It
also supports TCP/IP, FNA, SNA, JCA, ISDN, V.24/X.21,
V.35/RS449, ATM, and FDDI.
Highly reliable operating system
Value-added functions in Solaris
To reinforce mission critical support advantages,
reliability and serviceability have been improved by
providing specific value-added features, as part of the
operating system.
Hardware and software monitoring by Web-view.
Remote monitoring of system status and diagnosis of hardware
faults through log analysis.
Provision of menu-driven hardware monitoring, parameter setting,
display of log information, and machine management that displays
maintenance guidance during hot-swap operations.
New world-leading technology
GP7000F, through its adoption of international standards, the Solaris operating system,
and many new hardware technologies, delivers a UNIX server with the best in RAS
(Reliability, Availability, Serviceability).
[ GP7000F Rackmount type ]
GP7000F model 600R
Page 5
New high-performance technology
PCI bus
Data access and expansion are easy to manage.
GP7000F uses a 66/33MHz PCI bus I/O that supports
high-speed throughput of up to 3.1 GB/sec.
New high-performance 64-bit
RISC processor
-
SPARC64 GP
The GP7000F uses SPARC64 GP, a new 64-bit RISC
processor. Developed by Fujitsu and offering superb
performance, SPARC64 GP fully conforms to the SPARC
V9 architecture.
SPARC64 GP high-speed technology
The technology in SPARC64 GP provides improvement
in the number of simultaneously executable instructions
being processed. Its out-of-order function reduces
processing interrupts by executing instructions as
resources are available, rather than in the order of the
program. This ensures the maximum utilization of
available processing resources. SPARC64 GP also attains
very high-speed memory access by use of high-capacity
processor cache (1st level: 128KB, 2nd level: 2/4/8MB).
Techniques such as 4-way set associative, write-back
functions in 1st level cache, and predicted branches, also
reduce the load, avoid delays, and improve operational
performance.
High-performance system bus
Fujitsu offers world-class system performance through
a combination of a high-performance system bus, a
system bus controller, and the high-speed SPARC64 GP
processor.
The GP7000F system bus operates at an effective rate
of 5.6GB/sec. Use of the industry's highest-speed
crossbar switch maximizes CPU performance in
multiprocessor configurations. This is because more than
one bus can access memory and execute at the same
time using this crossbar.
A high-performance system controller was also
developed to ensure efficient use of the bus when
operating with the maximum 8 processors. The system
controller uses parallel caching techniques to obtain
efficient high-speed data transfer and improved memory
access through high-speed control of the crossbar
switch.
SPARC64 GP
SYSTEM
CONTROLLER
High-performance system bus
[Model 600]
Crossbar 128bit/90MHzX4
PCI
64bit/66MHzX4
64bit/33MHzX4
Fast bus switching for
memory access
CPUCPUCPU
I / O
Page 6
Mutual monitoring,error report,
logged records
Rotation monitoring/control
PSU monitoring/control
Temperature monitoring
AC error report
Processing device
I/O monitoring/control
Mutual monitoring
Error report
RCI
RCI
CPU
Fan
PSU
UPS
Temperature sensor
I/O
Monitoring board
System Monitoring
Other servers
Highly reliable hardware
The GP7000F,s high reliability comes from redundancy
and error detection and correction. Redundant system
components such as power supply units, disks and fans
are hot-plug. In addition, system control functions
provide high availability through the automatic isolation
of faulty processors, memory modules, and the I/O bus.
The 1st and 2nd level cache, as well as all memory on
the SPARC64 GP processor, have ECC. As a result, the
GP7000F reduces the ratio of processor and system
failures and ensures a very stable system for mission
critical business.
System control
GP7000F has excellent management facilities via its
independent system control processor. This processor
delivers very highly reliable and enhanced operation. It
continually detects and monitors for service irregularities
independent of main system status. It operates even
during processor failures and any system hang. A log is
maintained which can be used for interrogation and
reporting. It is also possible to watch and control all
systems including peripherals by an RCI (Remote
Cabinet Interface) through a GUI control screen.
Highly reliable file system
"SynfinityFile," from Fujitsu's clustering solution,
provides a superior service compared to standard file
systems. SynfinityFile looks after your data when system
failures occur. SynfinityFile log function provides for
rapid recovery of the file system following any system
failure, no matter the size of the file count. It handles
high-capacity, multi-volume files, and provides tuning
functions, including load-balancing, to greatly improve
I/O traffic.
"SynfinityDisk" improves data reliability and availability
through mirroring. SynfinityDisk allows data to be
accessed after hardware failure. Support for large
volumes of data is standard, as is a hot spare function for
fast data re-creation. SynfinityDisk significantly shortens
recovery times and the reconfiguring of systems in
clustered configurations.
High reliability means stable
system operation
Secure disk array system "GR720"
The GP7000F supports a high-performance and highly
reliable disk array system, the GR720. The GR720 is
scalable from 27GB up to 2.3TB.
The GR720 supports
RAID level 0/1/0+1/5
Ultra Wide SCSI, Ultra2 Wide SCSI, and Fibre Channel
interface
Dynamic Capacity Expansion function
Redundant configuration of the power supply and fans in
order to prevent operations from being affected by hardware
failure
Page 7
High Availability Cluster Systems
When your business cannot afford to stop, even for a short time, you need more than just
high reliability in each server. Such mission critical requirements are met by GP7000F's
clustering system. Multi-processor clusters linked to shared disk sub-systems minimize
service interruption when accidents or failures occur. Such clusters also provide
continued service when one server fails, or when components are off-line for routine
maintenance.
Range of solutions
The GP7000F's Clustering Systems offer a range of highly
available applications and environments in addition to the
basic durable and available system. The GP7000F's solutions
include highly available databases and transaction
processing systems, as well as network and shared printer
systems.
Availability
The hardware components are duplicated to maximize
system availability. This prevents total system failure or
data loss when a single component fails. In the event of a
potential server failure, the operational system can be
quickly transferred to a standby node to avoid service
disruption. The IP address, the operating node, MAC
address, and node name can also be transferred.
Hot standby technology
GP7000F can also be used in a "hot standby" configuration.
In this case, the standby node is in a hot standby condition
and is connected to the same shared disk system as the
operational node. This is different from the standard way of
transferring data and applications following a failure of an
operating node. With the GP7000F's "hot standby"
configuration, the time taken to restart the job is shortened
dramatically.
Operation
GP7000F clustering solutions remove the difficulties of
installation and operation that have previously restricted the
use of clustered solutions. Excellent system configuration
tools, such as the cluster installation wizard, automatic
hardware search and configuration function, WWW browserbased operational setup, and centralized control function
take away the complexities of cluster management. In
addition, these tools also greatly improve the levels of system
security in the operational system.
Scalability
A GP7000F clustering system not only provides improved
availability when data or processes are transferred due to
node failure, but it also dramatically improves overall system
performance through parallel processing.
Maximum 128CPUs
Scalable up to a maximum of 16 nodes/128CPUs by clustering.
Auto isolation
When a node fails, it is automatically separated from the cluster.
It can then be serviced offline. The remaining nodes in the
cluster reschedule the work and continue to operate without
service interruption.
High-speed interconnect system
Fujitsu's Synfinity high-speed interconnect technology is used
to transfer information between clustered nodes. Synfinity is the
world's fastest interconnect technology and provides a data
transfer rate of 240MB/sec. in both directions. This high-speed
transfer significantly improves the parallel database processing
performance of Fujitsu's SymfoWARE and Oracle's Parallel
Server systems.
Cluster Operation Control Screen
Cluster System Configuration
Shared Disk
Failed
Application Application
Hot Standby
Business
Clustering
System
Cluster
System base
Printing NFS Network
Database
Tran-
saction
Parallel
Database
Processing
Cluster basic
S/W
Disk
multiplex
path
Volume
Control
Highly
Reliable
File
System
High
Speed
Interconnect
(
VIA
)
LAN
multiplex
path
Availability Scalability
Page 8
SPARC64 is a registered trademark or trademark of SPARC.
International, Inc. in the United States and other countries used under license by Fujitsu Ltd.
Product bearing SPARC64 trademarks comply with SPARC V9 architecture developed by SPARC International, Inc.
Products bearing the SPARC trademarks are based on a architecture originally developed by Sun Microsystems, Inc.
Specifications are subject to change without notice. For the latest detailed information, contact your local representative.
All brand names and product names are trademarks and registered trademarks of their respective holders.
©2000 Fujitsu Limited. All rights reserved. Printed in Japan.
FUJITSU LIMITED
Business Development & Marketing Division
Marketing Group
Marunouchi Center Building
6-1, Marunouchi 1-chome, Chiyoda-ku, Tokyo 100-8211, Japan
Phone: +81-3- 3215-5255 Fax: +81-3-3215-5259
http://www.fujitsu.co.jp/index-e.html
(C)
2000 FUJITSU LIMITED
Printed in Japan
BK0068-5M
Fifth edition, March 2000
CPU
Cache
(
per CPU
)
Processor
Frequency
No. of CPU
SPEC int95
SPEC int_rate95
SPEC fp95
SPEC fp_rate95
14.0
212(2CPU
)
17.2
249(2CPU
)
Type
Main memory
L1
L2
Minimum
Maximum
Minimum
Maximum
Internal maximum
Disk option
Disk
Internal I/O
I/O Slots
Redundant
Hot plug
Standard I/O ports
Other functions
Dimension
Weight (kg)
Model 200
FDD
CD-ROM
4mm DAT
QIC
8mm Tape Drive
PCI(66/33MHz)
PCI(33MHz)
Disk
Power supply
Fan
Disk
Power supply
Fan
Internal Tape
WxDxH(mm)
SPARC64 GP
Model 200R Model 400A
SPARC64 GP
Model 400R
225MHz 250MHz 300MHz 300MHz 300MHz250MHz
2MB 4MB 8MB4MB 8MB4MB
250MHz250MHz 300MHz
1 2
1 4
15.9
250(2CPU
)
20.9
287(2CPU
)
19.2
( )
307(2CPU
)
24.0
( )
337(2CPU
)
4GB 8GB 16GB
16.0
( )
253
( )
22.9
( )
325
( )
19.1
( )
299(2CPU
)
27.3
( )
387(2CPU
)
16.0
498(4CPU
)
22.9
591(4CPU
)
19.2
( )
609(4CPU
)
30.2
( )
880(4CPU
)
16.0
498(4CPU
)
22.9
591(4CPU
)
19.2
( )
609(4CPU
)
30.2
( )
880(4CPU
)
64KB+64KB
256MB
256/512MB/1GB with ECC protection
64/128/256/512MB/1GB with
ECC protection
256/512MB/1GB/2GB
with ECC protection
Only in expansion
file unit
9.1GB
40TB 60TB 70TB
36.4GB 400.4GB400.4GB36.4GB145.6GB
3.5inch FDD as standard
CD-ROM 32 as standard
100BaseTX or 10BaseT x 1
RS232C x 2
Parallel x 1
Option
Option
Option
One of three can be installed
Option
Option
Option
One of three can be installed
2
4
YES
YES
(only for Expansion Cabinet/Unit)
YES YES YES
2 4(option)
4 8(option)
YES
9
4
YES
YES YES YES
YES YES
Only in expansion
file unit
YES
(only for Expansion Cabinet/Unit)
YES YES YES
Calendar, Auto power control function
UltraSCSI x 1
-
UltraSCSI x 1 or 2(option)UltraSCSI x 0 or 1(option)
-
482 x 779 x 174
40
230 x 667 x 700
43
482 x 814 x 307
65
500 x 882 x 700
175
800 x 900 x 1200
314
Estimation
Pedestal/Floor-stand Rackmount Pedestal/Floor-stand Rackmount
Memory module
YES
36.4GB
8
482 x 787 x 530
120
Model 600
SPARC64 GP
300MHz275MHz
8MB
2 8
17.6
1093(8CPU
)
27.1
1487(8CPU
)
19.2
1208(8CPU
)
30.5
1622(8CPU
)
Pedestal/Floor-stand
Model 600R
300MHz275MHz
17.6
( )
1093(8CPU
)
27.1
( )
1487(8CPU
)
19.2
( )
1208(8CPU
)
30.5
( )
1622(8CPU
)
Rackmount
9.1GB/18.2GB (10,000rpm)
Loading...